AANA Email Send Guardrail Skill

• Analyzed: May 3, 2026, 8:26 PM
• Findings: 1
• Version: 1.0.0
• Hash: 627ff9a03e0d5022545daeb1509d17638703bb0918fadf3f036ca5ae1e4c582c
• Source: palm
• External report: View on VirusTotal

Findings (1)

This is a defensive, instruction-only skill bundle designed to implement safety guardrails for AI agents performing email-related tasks. The instructions in SKILL.md and manifest.json explicitly forbid the exfiltration of sensitive data (API keys, tokens, PII), mandate explicit user approval before sending messages, and enforce a 'redacted summary' approach to minimize data exposure. There is no executable code, no network activity, and no evidence of malicious intent or prompt-injection vulnerabilities.